DLDN-Bench
benchmark
DLDN-Bench: benchmark. Benchmark framework for deep-learning de novo peptide sequencing in proteomics. Derives evaluation datasets from human muscle biopsy MS data on PRIDE annotated by…
Benchmark framework for deep-learning de novo peptide sequencing in proteomics. Derives evaluation datasets from human muscle biopsy MS data on PRIDE annotated by cross-engine consensus, and reports precision / coverage of recent DL tools (and classical baselines) against that pseudo-ground-truth.
| Kind | benchmark |
| Acquisition | DDA |
Code
Live stars, open issues and last-push figures are on the Code activity chart.
Data
What the papers describing this method trained it on and reported its results on, as each paper states it. A version is named only where the paper names one.
Also used, purpose not recorded
- DNDL-Bench: Annotated Benchmark Datasets + Prediction files from de novo models (as deposited)
- Engineering of human myotubes towards a mature metabolic and contractile phenotype (as deposited)
- Human (21d bed rest) Muscle LC-MSMS (as deposited)
- Proteomics of slow and fast human muscle fibers reveals extensive fiber type-specific adaptations in response to exercis (as deposited)
- Temporal phosphoproteomics reveals circuitry of phased propagation in insulin signaling (as deposited)
Paper describing it
- DLDN-Bench: A Benchmark Framework for Deep Learning de Novo Peptide Sequencing in Proteomics (2026, bioRxiv, preprint)